{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JX5VEIJ3QA3PDVHULC6V7WBOG6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e0553b9f1611f5d10e2888cc2c149975b03b0309c9c3404deb9ffbd51c74f945","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T07:12:07Z","title_canon_sha256":"cd73e61fa79247cca2f3ac4035de58066941e8e04278dfa02397796c04e2ae11"},"schema_version":"1.0","source":{"id":"2404.17808","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17808","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17808v3","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17808","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"JX5VEIJ3QA3P","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"JX5VEIJ3QA3PDVHU","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"JX5VEIJ3","created_at":"2026-07-05T09:34:35Z"}],"graph_snapshots":[{"event_id":"sha256:5837c7f746cea2d412372dfdca4713410a8500085881f39435b59992ac4f616f","target":"graph","created_at":"2026-07-05T09:34:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.17808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte Pair Encoding (BPE) serves as a foundation method for text tokenization in the Natural Language Processing (NLP) field. Despite its wide adoption, the original BPE algorithm harbors an inherent flaw: it inadvertently introduces a frequency imbalance for tokens in the text corpus. Since BPE iteratively merges the most frequent token pair in the text corpus to generate a new token and keeps all generated tokens in the vocabulary, it unavoidably holds tokens that primarily act as components of a longer token and appear infrequently on their own. We term such tokens as Scaffold Tokens. Due to","authors_text":"Guiguang Ding, Haoran Lian, Hui Chen, Jianwei Niu, Jungong Han, Peng Liu, Shasha Mo, Yizhe Xiong, Zhenpeng Su, Zijia Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T07:12:07Z","title":"Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17808","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1bc3c56d7fb63ace68ae436bd6723c84b0c62c11d27b040d3d86cb82f0511bdb","target":"record","created_at":"2026-07-05T09:34:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e0553b9f1611f5d10e2888cc2c149975b03b0309c9c3404deb9ffbd51c74f945","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T07:12:07Z","title_canon_sha256":"cd73e61fa79247cca2f3ac4035de58066941e8e04278dfa02397796c04e2ae11"},"schema_version":"1.0","source":{"id":"2404.17808","kind":"arxiv","version":3}},"canonical_sha256":"4dfb52213b8036f1d4f458bd5fd82e379ef326e24e7b04b5b9c018f19e7763c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dfb52213b8036f1d4f458bd5fd82e379ef326e24e7b04b5b9c018f19e7763c8","first_computed_at":"2026-07-05T09:34:35.646915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:35.646915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c9bN1aQ6VzHKjC84xnjApIwBvAl1L78F4N8PZM7cwsLn0h+u6kzDLdpP5vkPiNW5A5ObBJbhLuQeUc0bEzxdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:35.647431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17808","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bc3c56d7fb63ace68ae436bd6723c84b0c62c11d27b040d3d86cb82f0511bdb","sha256:5837c7f746cea2d412372dfdca4713410a8500085881f39435b59992ac4f616f"],"state_sha256":"e62e66b40aa2add55e42a202788ac5937f1879a7ed61bb0cc67cbfdf73790166"}